Related papers: Separable Self and Mixed Attention Transformers fo…

Transformer-based models have achieved remarkable results in low-level vision tasks including image super-resolution (SR). However, early Transformer-based approaches that rely on self-attention within non-overlapping windows encounter…

Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of…

Mainstream visual object tracking frameworks predominantly rely on template matching paradigms. Their performance heavily depends on the quality of template features, which becomes increasingly challenging to maintain in complex scenarios…

Multivariate time series (MTS) analysis prevails in real-world applications such as finance, climate science and healthcare. The various self-attention mechanisms, the backbone of the state-of-the-art Transformer-based models, efficiently…

Vision transformers have demonstrated remarkable success in classification by leveraging global self-attention to capture long-range dependencies. However, this same mechanism can obscure fine-grained spatial details crucial for tasks such…

Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real…

Trackers based on Siamese network have shown tremendous success, because of their balance between accuracy and speed. Nevertheless, with tracking scenarios becoming more and more sophisticated, most existing Siamese-based approaches ignore…

Transformer models have achieved promising performances in point cloud segmentation. However, most existing attention schemes provide the same feature learning paradigm for all points equally and overlook the enormous difference in size…

Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…

Multi-modal feature fusion as a core investigative component of RGBT tracking emerges numerous fusion studies in recent years. However, existing RGBT tracking methods widely adopt fixed fusion structures to integrate multi-modal feature,…

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges…

Transformer-based deep neural networks have achieved great success in various sequence applications due to their powerful ability to model long-range dependency. The key module of Transformer is self-attention (SA) which extracts features…

Although recent Siamese network-based trackers have achieved impressive perceptual accuracy for single object tracking in LiDAR point clouds, they usually utilized heavy correlation operations to capture category-level characteristics only,…

Despite great progress in multimodal tracking, these trackers remain too heavy and expensive for resource-constrained devices. To alleviate this problem, we propose LightFC-X, a family of lightweight convolutional RGB-X trackers that…

Most Siamese network-based trackers perform the tracking process without model update, and cannot learn targetspecific variation adaptively. Moreover, Siamese-based trackers infer the new state of tracked objects by generating axis-aligned…

Time series forecasting is crucial for applications across multiple domains and various scenarios. Although Transformer models have dramatically advanced the landscape of forecasting, their effectiveness remains debated. Recent findings…

In recent years, significant progress has been made on the research of crowd counting. However, as the challenging scale variations and complex scenes existed in crowds, neither traditional convolution networks nor recent Transformer…

Conventional multi-object tracking (MOT) systems are predominantly designed for pedestrian tracking and often exhibit limited generalization to other object categories. This paper presents a generalized tracking framework capable of…

One-stream Transformer-based trackers have demonstrated remarkable performance by concatenating template and search region tokens, thereby enabling joint attention across all tokens. However, enabling an excessive proportion of background…

State-of-the-art models for medical image segmentation achieve excellent accuracy but require substantial computational resources, limiting deployment in resource-constrained clinical settings. We present SegMate, an efficient 2.5D…